Gaps in the type 2 diabetes care cascade: a national perspective using South Africa's National Health Laboratory Service (NHLS) database.

BACKGROUND: Research out of South Africa estimates the total unmet need for care for those with type 2 diabetes mellitus (diabetes) at 80%. We evaluated the care cascade using South Africa's National Health Laboratory Service (NHLS) database and assessed if HIV infection impacts progression through its stages. METHODS: The cohort includes patients from government facilities with their first glycated hemoglobin A1c (HbA1c) or plasma glucose (fasting (FPG); random (RPG)) measured between January 2012 to March 2015 in the NHLS. Lab-diagnosed diabetes was defined as HbA1c ≥ 6.5%, FPG ≥ 7.0mmol/l, or RPG ≥ 11.1mmol/l. Cascade stages post diagnosis were retention-in-care and glycaemic control (defined as an HbA1c < 7.0% or FPG < 8.0mmol/l or RPG < 10.0mmol/l) over 24-months. We estimated gaps at each stage nationally and by people living with HIV (PLWH) and without (PLWOH). RESULTS: Of the 373,889 patients tested for diabetes, 43.2% had an HbA1c or blood glucose measure indicating a diabetes diagnosis. Amongst those with lab-diagnosed diabetes, 30.9% were retained-in-care (based on diabetes labs) and 8.7% reached glycaemic control by 24-months. Prevalence of lab-diagnosed diabetes in PLWH was 28.6% versus 47.3% in PLWOH. Among those with lab-diagnosed diabetes, 34.3% of PLWH were retained-in-care versus 30.3% PLWOH. Among people retained-in-care, 33.8% of PLWH reached glycaemic control over 24-months versus 28.6% of PLWOH. CONCLUSIONS: In our analysis of South Africa's NHLS database, we observed that 70% of patients diagnosed with diabetes did not maintain in consistent diabetes care, with fewer than 10% reaching glycemic control within 24 months. We noted a disparity in diabetes prevalence between PLWH and PLWOH, potentially linked to different screening methods. These differences underscore the intricacies in care but also emphasize how HIV care practices could guide better management of chronic diseases like diabetes. Our results underscore the imperative for specialized strategies to bolster diabetes care in South Africa.

Potential immunosuppressive clonal hematopoietic mutations in tumor infiltrating immune cells in breast invasive carcinoma.

A hallmark of cancer is a tumor cell's ability to evade immune destruction. Somatic mutations in tumor cells that prevent immune destruction have been extensively studied. However, somatic mutations in tumor infiltrating immune (TII) cells, to our knowledge, have not been previously studied. Understandably so since normal hematopoiesis prevents the accumulation of somatic mutations in immune cells. However, clonal hematopoiesis does result in the accumulation of somatic mutations in immune cells. These mutations cannot "drive" tumor growth, however, they may "facilitate" it by inhibiting an effective anti-tumor immune response. To identify potential immunosuppressive clonal hematopoietic (CH) mutations in TII cells, we analyzed exome and RNA sequencing data from matched tumor and normal blood samples, and single-cell RNA sequencing data, from breast cancer patients. We selected mutations that were somatic, present in TII cells, clonally expanded, potentially pathogenic, expressed in TII cells, unlikely to be a passenger mutation, and in immune response associated genes. We identified eight potential immunosuppressive CH mutations in TII cells. This work is a first step towards determining if immunosuppressive CH mutations in TII cells can affect the progression of solid tumors. Subsequent experimental confirmation could represent a new paradigm in the etiology of cancer.

Hypertension, renin-angiotensin-aldosterone-system-blocking agents, and COVID-19.

BACKGROUND: There have been concerns regarding the safety of renin-angiotensin-aldosterone-system (RAAS)-blocking agents including angiotensin-converting enzyme inhibitors (ACEI) and angiotensin receptor blockers (ARB) during the coronavirus disease 2019 (COVID-19) pandemic. This study sought to evaluate the impact of hypertension and the use of ACEI/ARB on clinical severity in patients with COVID-19. METHODS: A total of 3,788 patients aged 30 years or older who were confirmed with COVID-19 with real time reverse transcription polymerase chain reaction were identified from a claims-based cohort in Korea. The primary study outcome was severe clinical events, a composite of intensive care unit admission, need for ventilator care, and death. RESULTS: Patients with hypertension (n = 1,190, 31.4 %) were older and had higher prevalence of comorbidities than those without hypertension. The risk of the primary study outcome was significantly higher in the hypertension group, even after multivariable adjustment (adjusted odds ratio [aOR], 1.67; 95 % confidence interval [CI], 1.04 to 2.69). Among 1,044 patients with hypertensive medical treatment, 782 (74.9 %) were on ACEI or ARB. The ACEI/ARB subgroup had a lower risk of severe clinical outcomes compared to the no ACEI/ARB group, but this did not remain significant after multivariable adjustment (aOR, 0.68; 95 % CI, 0.41 to 1.15). CONCLUSIONS: Patients with hypertension had worse COVID-19 outcomes than those without hypertension, while the use of RAAS-blocking agents was not associated with increased risk of any adverse study outcomes. The use of ACE inhibitors or ARBs did not increase the risk of adverse COVID-19 outcomes, supporting current guidance to continue these medications when indicated.

Impacts of social distancing policies on mobility and COVID-19 case growth in the US.

Social distancing remains an important strategy to combat the COVID-19 pandemic in the United States. However, the impacts of specific state-level policies on mobility and subsequent COVID-19 case trajectories have not been completely quantified. Using anonymized and aggregated mobility data from opted-in Google users, we found that state-level emergency declarations resulted in a 9.9% reduction in time spent away from places of residence. Implementation of one or more social distancing policies resulted in an additional 24.5% reduction in mobility the following week, and subsequent shelter-in-place mandates yielded an additional 29.0% reduction. Decreases in mobility were associated with substantial reductions in case growth two to four weeks later. For example, a 10% reduction in mobility was associated with a 17.5% reduction in case growth two weeks later. Given the continued reliance on social distancing policies to limit the spread of COVID-19, these results may be helpful to public health officials trying to balance infection control with the economic and social consequences of these policies.

Predicting Inpatient Medication Orders From Electronic Health Record Data.

In a general inpatient population, we predicted patient-specific medication orders based on structured information in the electronic health record (EHR). Data on over three million medication orders from an academic medical center were used to train two machine-learning models: A deep learning sequence model and a logistic regression model. Both were compared with a baseline that ranked the most frequently ordered medications based on a patient's discharge hospital service and amount of time since admission. Models were trained to predict from 990 possible medications at the time of order entry. Fifty-five percent of medications ordered by physicians were ranked in the sequence model's top-10 predictions (logistic model: 49%) and 75% ranked in the top-25 (logistic model: 69%). Ninety-three percent of the sequence model's top-10 prediction sets contained at least one medication that physicians ordered within the next day. These findings demonstrate that medication orders can be predicted from information present in the EHR.

Wearable sensors for Parkinson's disease: which data are worth collecting for training symptom detection models.

Machine learning algorithms that use data streams captured from soft wearable sensors have the potential to automatically detect PD symptoms and inform clinicians about the progression of disease. However, these algorithms must be trained with annotated data from clinical experts who can recognize symptoms, and collecting such data are costly. Understanding how many sensors and how much labeled data are required is key to successfully deploying these models outside of the clinic. Here we recorded movement data using 6 flexible wearable sensors in 20 individuals with PD over the course of multiple clinical assessments conducted on 1 day and repeated 2 weeks later. Participants performed 13 common tasks, such as walking or typing, and a clinician rated the severity of symptoms (bradykinesia and tremor). We then trained convolutional neural networks and statistical ensembles to detect whether a segment of movement showed signs of bradykinesia or tremor based on data from tasks performed by other individuals. Our results show that a single wearable sensor on the back of the hand is sufficient for detecting bradykinesia and tremor in the upper extremities, whereas using sensors on both sides does not improve performance. Increasing the amount of training data by adding other individuals can lead to improved performance, but repeating assessments with the same individuals-even at different medication states-does not substantially improve detection across days. Our results suggest that PD symptoms can be detected during a variety of activities and are best modeled by a dataset incorporating many individuals.

Scalable and accurate deep learning with electronic health records.

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two US academic medical centers with 216,221 adult patients hospitalized for at least 24 h. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting: in-hospital mortality (area under the receiver operator curve [AUROC] across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios. In a case study of a particular prediction, we demonstrate that neural networks can be used to identify relevant information from the patient's chart.

The Supervised Hierarchical Dirichlet Process.

We propose the supervised hierarchical Dirichlet process (sHDP), a nonparametric generative model for the joint distribution of a group of observations and a response variable directly associated with that whole group. We compare the sHDP with another leading method for regression on grouped data, the supervised latent Dirichlet allocation (sLDA) model. We evaluate our method on two real-world classification problems and two real-world regression problems. Bayesian nonparametric regression models based on the Dirichlet process, such as the Dirichlet process-generalised linear models (DP-GLM) have previously been explored; these models allow flexibility in modelling nonlinear relationships. However, until now, hierarchical Dirichlet process (HDP) mixtures have not seen significant use in supervised problems with grouped data since a straightforward application of the HDP on the grouped data results in learnt clusters that are not predictive of the responses. The sHDP solves this problem by allowing for clusters to be learnt jointly from the group structure and from the label assigned to each group.